AI VFX and experiments

63 of 3,062 videos

450 AI VFX and experiments, posted in public on X and Threads by the 42 creators who made them. Open any video to see who made it and what they used.

Train Phone Stunt: Previz vs Seedance Final

I created a full short film using free open source AI video models. I jumped into the role of the wizard Trogus and transformed myself into him using AI. Imagine what kind of movies you would have made if you had this tool as a kid!

Mickmumpitz284KX

This time freeze effect is going viral and it's super easy to make using Seedance 2.0 Check the reply for the prompt.

CHRIS FIRST271KX

point and click ⬅️ Made in @ComfyUI + @Photoshop + @AdobeAE with GPT Image 2.0 and Wan 2.2 I2V ✏️🤖

Ingi Erlingsson 🪄271KX

With this prompt, you can sit courtside for Game 3 as the Knicks look to sweep the 76ers in Philly. Prompts below. Inspired by @johnAGI168

CHRIS FIRST211KX

We wanted full control for our new AI movie “Paper Jam”, so we hand-animated all poses in an AI-generated 3D space. Scenes were then rendered using @bfl_ml Flux with regional custom character LoRAs for consistency and interpolated with @Kling_ai Tutorial + free workflows👇

Mickmumpitz181KX

Playing around with workflows at @LumaLabsAI @DreamLabLA

Jon Finger138KX

This entire anime sequence started from ONE Canvas. 👀🔥 I wanted to see how far I could push the new Canvas-first workflow in the upgraded version of Dreamina on a real project. So I built everything inside the same Canvas: → Created my characters → Built detailed Character Sheets → Locked their vis

Pierrick Chevallier | IA88.7KX

For my real-life Toy Story short film, I built a workflow to control AI characters using puppets, paper cutouts, or animated previz! And yeah I know… @CorridorDigital recently had a very similar idea. But they used a different technique! Let’s compare👇

Mickmumpitz59.4KX

You can now turn images into explorable 3D worlds. Locally. For free. The method involves piloting a virtual 360 degree drone through your scene to map out your world and generate a synthetic dataset for gaussian splat training. Here is how it works 👇

Mickmumpitz54.5KX

The Ibiza Final Boss... Doing dumb internet stuff. With Weavy + Minimax-02. TOOLS: + Weavy: Workflow Build + Flux Kontext: Image Gen + Minimax-02: Video gen + Runway Act-2: MoCap + Runway Aleph: Vid edits (More details in thread)

Rory Flynn49.8KX

I love open source AI in @ComfyUI because it lets me control every step. For this spaceship shot I tracked the camera, designed layout geometry in Blender, exported depth maps, prompted the final look with an AI image editor, and jumped into Photoshop to clean it all up.

Mickmumpitz48.1KX

Changing the camera with MiniMax H3 and SAM 3D Body while keeping the environment consistent. If I'd known I'd get it working this fast, I would have said something smart... More examples below!

Mickmumpitz25.4KX

Found footage from Fast & the Furious 🤯 Using Opus 5.5 + Blender + Seedance 2.5 To rebuild (block) the scene in 3D + generate with SD2.5. It's just weird we can do this. The crash physics got me. (Refs + Prompt in Thread)

Rory Flynn24.9KX

Here's the tutorial! This video combines AI-generated elements (balloon, kite, surfboard, and backgrounds) with my own real-world practical effects and stop motion. I made this for #AdobeFirefly Thanks @Adobe for sponsoring my art

Karen X. Cheng21.1KX

Seedance 2.5 Omni Reference dance transfer workflow

Imagine making a tutorial on how you created and edited a video with Claude… using a video you ALSO edited with Claude 🤯 Mad stuff. To everyone who's been asking how I made the Chowdeck ad with Claude, here's the full tutorial. You're welcome 😌 Reply CHOWDECK and I'll send you the website link + m

Precious Jimoh13.2KX

None of this was filmed. I built a whole world in CineMap, directed every shot, and turned it into cinema with @TapNow_AI Here's how it works:

Gizem Akdag12.5KX

first cut30 yapping video not perfect but we're getting the reps in ;)

Channel: Explore this before and after - to see how live footage could gain some expressive stylization in our Paranormal studio "kitchen". Can you imagine whole movie in this style? 🎬🍿🎥

Jakub Javora10.1KX

Used GPT Image 2 & Seedance 2.0 to create this “tiny world” effect My prompts here: This is day 10 of extremely easy edits Edited with @Artlist_io

Karen X. Cheng5.9KX

🎥⚗🎨 In studio Paranormal - We were always developing different art styles and rotoscope/animation techniques. We are creating not only different art vibe but unique motion feel as well.

Jakub Javora5.4KX

Seedance 2.0 is pretty good at making videos of your cat. I made this with just 1 photo My tutorial and prompts here: This is day 8 of extremely easy edits Edited with @magnific

Karen X. Cheng5.2KX

iphone works too! @koldo2k

JC | AI Creative Director4.8KX